Contextualization and Recommendation of Annotations to Enhance Information Exchange in Assembly Assistance
J.UCS Journal of Universal Computer Science
Increasingly flexible production processes require intelligent assistance systems containing information and knowledge to maintain high quality and efficiency. To ensure a reliable supply of information, it is of great importance to find easy and fast ways to record and store "new" information, as well as to provide a sensible mechanism to supply the information when needed. In this paper an approach is presented that uses annotations in combination with a formalized knowledge base that represents the work domain. This pre-condition enables a context-based annotation recommendation. A framework is proposed to integrate different factors to measure the relevance of an annotation according to a given situation. The approach is illustrated using the example of an assembly assistance system. To evaluate the users' attitude regarding annotations as instruction support and to test the system's capabilities when handling a great number of annotations some studies were performed and analyzed.
Facilitating Information Exchange in Assembly Assistance by Recommending Contextualized Annotations
RS-BDA '16. Proceedings of the First Workshop on Recommender Systems and Big Data Analytics
Workshop on Recommender Systems and Big Data Analytics (RS-BDA) <1, 2016, Graz, Austria>
To maintain an equally high quality and efficiency in production processes despite the increased flexibility, information and knowledge are the company's strategically most important resources today. At the same time the intellectual re- sources are difficult to capture and manage, thus requiring intelligent assistance systems that support the individuals by providing suitable means for interacting with information. Therefore, it is of great importance to find an easy and fast way to record and store "new" information, as well as to provide a sensible mechanism to provide the information when needed. We propose to use annotations in combination with a formalized knowledge base that represents the work domain to enable an intuitive (semi-)automatic information contextualization. This pre-condition enables a context-based an- notation recommendation allowing for the annotations to be provided automatically for a better information communication. We propose a framework to integrate different factors to measure the relevance of an annotation according to a given situation and illustrate the results of our work using the example of an assembly assistance system.
Annotated Domain Ontologies for the Visualization of Heterogeneous Manufacturing Data
Human Interface and the Management of Information. Proceedings Part I
International Conference on Human Interface and the Management of Information (HIMI) <2015, Los Angeles, CA, USA>
Manufacturing processes such as monitoring and controlling typically confront the user with a variety of heterogeneous data sources and systems. The cognitive efforts to summarize and combine the data from these different sources affect the user's efficiency. Our goal is to support the user in his work task by integrating the data and presenting them in a more perceivable way. Hence, we introduce an approach in which different data sources are integrated in an annotated semantic knowledge base: our domain ontology. Based on this ontology, contextually relevant data for a specific work task is selected and embedded into a meta-visualization providing an overview of the data based on the user's mental model. Two systems finally exemplify the usage of our approach.
Annotation-Based Feature Extraction from Sets of SBML Models
Journal of Biomedical Semantics
Background: Model repositories such as BioModels Database provide computational models of biological systems for the scientific community. These models contain rich semantic annotations that link model entities to concepts in well-established bio-ontologies such as Gene Ontology. Consequently, thematically similar models are likely to share similar annotations. Based on this assumption, we argue that semantic annotations are a suitable tool to characterize sets of models. These characteristics improve model classification, allow to identify additional features for model retrieval tasks, and enable the comparison of sets of models. Results: In this paper we discuss four methods for annotation-based feature extraction from model sets. We tested all methods on sets of models in SBML format which were composed from BioModels Database. To characterize each of these sets, we analyzed and extracted concepts from three frequently used ontologies, namely Gene Ontology, ChEBI and SBO. We find that three out of the methods are suitable to determine characteristic features for arbitrary sets of models: The selected features vary depending on the underlying model set, and they are also specific to the chosen model set. We show that the identified features map on concepts that are higher up in the hierarchy of the ontologies than the concepts used for model annotations. Our analysis also reveals that the information content of concepts in ontologies and their usage for model annotation do not correlate. Conclusions: Annotation-based feature extraction enables the comparison of model sets, as opposed to existing methods for model-to-keyword comparison, or model-to-model comparison.
Plant@Hand: From Activity Recognition to Situation-based Annotation Management at Mobile Assembly Workplaces
iWOAR 2015 - 2nd international Workshop on Sensor-based Activity Recognition and Interaction
International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>
This paper describes an approach towards situation-based annotation management on the basis of work integrated activity recognition and situation detection. We motivate situation-based annotations as a means for collecting and processing contextual knowledge on the work domain in order to improve the quality of information assistance at mobile assembly workplaces. Especially, when we make use of automated processes which aim to detect the worker's ongoing activities and situations, we have to deal at the same time with errors and wrongly inferred assumptions on reality. Here we see the strengths of annotation management which can be used to revise contextual background knowledge, required for determining the autonomous behavior, in case of errors and deviations between inferred and real situations.
Processing Manufacturing Knowledge with Ontology-based Annotations and Cognitive Architectures
International Conference on Knowledge Management and Data-driven Business (I-KNOW) <15, 2015, Graz, Austria>
Advanced manufacturing promises an evolution of industrial production processes. However, today's manufacturing systems lack a common strategy on how to combine factual, procedural, and conceptual knowledge in order to streamline production processes. This specifically applies for manufacturing assembly assistance where the major share of procedural and conceptual knowledge is not yet automatically processable. In our paper we propose the usage of ontology-based annotations as missing link between the tacit knowledge of the worker and the intelligent assistance system. We show the deeper integration of conceptual knowledge modeled in ontology-based annotations with procedural knowledge in cognitive architectures. Additionally, in our approach annotations act as a mean of communication between the workers and with the system. We show key aspects of a prototypical integration of our approach within a smart assembly assistance system which supplies the worker with task related information.
Properties of a Peripheral Head-Mounted Display (PHMD)
HCI International 2015 - Posters' Extended Abstracts. Proceedings Part I
International Conference on Human-Computer Interaction (HCII) <17, 2015, Los Angeles, CA, USA>
In this paper we propose a definition for Peripheral Head-Mounted Display (PHMD) for Near Field Displays. This paper introduces a taxonomy for head-mounted displays that is based on the property of its functionality and the ability of our human eye to perceive peripheral information, instead of being technology-dependent. The aim of this paper is to help designers to understand the perception of the human eye, as well as to discuss the factors one needs to take into consideration when designing visual interfaces for PHMDs. We envision this term to help classifying devices such as Google Glass, which are often misclassified as a Head-Up Display (HUD) following NASA’s definition.
Towards Integration and Management of Contextualized Information in the Manufacturing Environment by Digital Annotations
Proceedings of the International Summer School on Visual Computing 2015
International Summer School on Visual Computing <1, 2015, Rostock, Germany>
Advanced manufacturing promises an evolution of industrial production processes by increasing flexibility and specialization of work tasks to deal with mass customization. To maintain a high quality and efficiency despite this increasing customization or even improve them, intelligent assistance systems are required supporting the workers. This paper describes how to integrate digital information in a manufacturing environment, where workers use assistance systems to access task related information. To explain requirements and constraints of assistance Systems, a survey was conducted. Based on the results of this survey, a conceptual approach is specified that focuses on quick and easy access to relevant information via a tablet. To provide manufacturing workers with relevant information, a method is presented to measure information relevance based on an ontology. A demonstrative scenario describes the application of the conceptual approach.
Annotation-Based Feature Extraction from Sets of SBML Models
Data Integration in the Life Sciences
International Conference on Data Integration in the Life Sciences (DILS) <10, 2014, Lisbon, Portugal>
Model repositories such as BioModels Database provide computational models of biological systems for the scientific community. These models contain rich semantic annotations that link model entities to concepts in well-established bio-ontologies such as Gene Ontology. Consequently, thematically similar models are likely to share similar annotations. Based on this assumption, we argue that semantic annotations are a suitable tool to characterize sets of models. These characteristics can then help to classify models, to identify additional features for model retrieval tasks, or to enable the comparison of sets of models. In this paper, we present four methods for annotation-based feature extraction from model sets. All methods have been used with four different model sets in SBML format and taken from BioModels Database. To characterize each of these sets, we analyzed and extracted concepts from three frequently used ontologies for SBML models, namely Gene Ontology, ChEBI and SBO. We find that three of the four tested methods are suitable to determine characteristic features for model sets. The selected features vary depending on the underlying model set, and they are also specific to the chosen model set. We show that the identified features map on concepts that are higher up in the hierarchy of the ontologies than the concepts used for model annotations. Our analysis also reveals that the information content of concepts in ontologies and their usage for model annotation do not correlate.
Konzept zur Arbeitsgeräteerkennung mittels Vibrationsanalyse durch Methoden des maschinellen Lernens
WIWITA 2014. Proceedings
Wismarer Wirtschaftsinformatiktage (WIWITA) <9, 2014, Wismar, Germany>
Die Verwendung verschiedenster Arbeitsgeräte unterstützt den Arbeiter bei seiner Tätigkeit und ist im industriellen Umfeld nicht mehr wegzudenken. Viele elektrisch oder pneumatisch betriebene Arbeitsgeräte erzeugen im Betrieb Vibrationen, die auf den Anwender übertragen werden. Überschreiten diese über längere Zeit ein gewisses Maß, kann dieses langfristig zu Beeinträchtigungen und Schädigungen bis hin zur Berufsunfähigkeit führen. Entsprechend der Lärm- und Vibrations-Arbeitsschutzverordnung ist an Arbeitsplätzen mit potentieller Exposition gegenüber Vibrationen eine laufende Gefährdungsanalyse vorgeschrieben. In der Praxis geschieht dies derzeit stichprobenartig durch externe Experten oder behelfsmäßig anhand von Zeitschätzungen und Tabellenwerten. In der einschlägigen Literatur wird darauf verwiesen, dass die tatsächliche Exposition dabei häufig überschätzt wird, wodurch den betroffenen Unternehmen ein finanzieller Schaden entsteht. In der vorliegenden Arbeit wird ein Konzept vorgestellt, um Hand-Arm-Vibrationen durch eine handelsübliche Smartwatch abzuschätzen. Dabei werden durch verschiedene Sensoren der Smartwatch die Beschleunigungskräfte (Akzelerometer), die Winkeländerungen (Gyroskop) sowie die Geräusche (Mikrofon) gemessen. Mit Methoden des maschinellen Lernens können auf dieser Grundlage die verwendeten Arbeitsgeräte sowie die genaue Nutzungsdauer bestimmt werden. Auf diese Weise wird mit preisgünstiger COTS-Hardware eine wesentlich genauere Bewertung vibrationsbedingter Gefährdungen am Arbeitsplatz möglich. Das System kann den Träger bei zu hoher Vibrationsbelastung selbstständig warnen. Darüber hinaus können die durchgeführten Arbeiten bei der Ausführung automatisch oder manuell annotiert werden. Um die grundlegende Machbarkeit des Konzeptes zu überprüfen, wurden unter Verwendung von Arbeitsgeräten aus sechs Geräteklassen mit 13 Probanden Messdaten erhoben und mit dem beschriebenen Verfahren analysiert. Dabei zeigte sich zunächst, dass der Gebrauch stark vibrierender Arbeitsgeräte mit hoher Präzision von Inaktivität abgegrenzt werden kann, wodurch eine Zeiterfassung der Gerätenutzung ermöglicht wird. Darüber hinaus konnten im Laborumfeld einzelne Werkzeuge auch zwischen verschiedenen Probanden wiedererkannt werden. Die Einsatzfähigkeit unter praxisnahen Bedingungen muss jedoch in weiteren Arbeiten untersucht werden.